DeBoNet: A deep bone suppression model ensemble to improve disease detection in chest radiographs

• Published in: PloS one 2022-03, Vol.17 (3), p.e0265691-e0265691
• Main Authors: Rajaraman, Sivaramakrishnan, Cohen, Gregg, Spear, Lillian, Folio, Les, Antani, Sameer
• Format: Article
• Language: English
• Subjects: Abnormalities; Analysis; Artificial intelligence; Artificial neural networks; Automation; Biology and Life Sciences; Bones; Business metrics; Chest; Classification; Clavicle - diagnostic imaging; Computer and Information Sciences; Confidence intervals; Coronaviruses; COVID-19; COVID-19 - diagnostic imaging; Decision making; Disease detection; Humans; Lung Diseases - diagnostic imaging; Medicine and Health Sciences; Metadata; Modelling; National libraries; Neural networks; Neural Networks, Computer; Physical Sciences; Radiography; Radiography, Thoracic - methods; Radiology; Research and Analysis Methods; Ribs - diagnostic imaging; Signal to noise ratio; Social Sciences; Soft tissues; Software; Visibility
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0265691

Automatic detection of some pulmonary abnormalities using chest X-rays may be impacted adversely due to obscuring by bony structures like the ribs and the clavicles. Automated bone suppression methods would increase soft tissue visibility and enhance automated disease detection. We evaluate this hypothesis using a custom ensemble of convolutional neural network models, which we call DeBoNet, that suppresses bones in frontal CXRs. First, we train and evaluate variants of U-Nets, Feature Pyramid Networks, and other proposed custom models using a private collection of CXR images and their bone-suppressed counterparts. The DeBoNet, constructed using the top-3 performing models, outperformed the individual models in terms of peak signal-to-noise ratio (PSNR) (36.7977±1.6207), multi-scale structural similarity index measure (MS-SSIM) (0.9848±0.0073), and other metrics. Next, the best-performing bone-suppression model is applied to CXR images that are pooled from several sources, showing no abnormality and other findings consistent with COVID-19. The impact of bone suppression is demonstrated by evaluating the gain in performance in detecting pulmonary abnormality consistent with COVID-19 disease. We observe that the model trained on bone-suppressed CXRs (MCC: 0.9645, 95% confidence interval (0.9510, 0.9780)) significantly outperformed (p < 0.05) the model trained on non-bone-suppressed images (MCC: 0.7961, 95% confidence interval (0.7667, 0.8255)) in detecting findings consistent with COVID-19 indicating benefits derived from automatic bone suppression on disease classification. The code is available at https://github.com/sivaramakrishnan-rajaraman/Bone-Suppresion-Ensemble.